sl@0: /*
sl@0: * Copyright (c) 1997-2009 Nokia Corporation and/or its subsidiary(-ies).
sl@0: * All rights reserved.
sl@0: * This component and the accompanying materials are made available
sl@0: * under the terms of "Eclipse Public License v1.0"
sl@0: * which accompanies this distribution, and is available
sl@0: * at the URL "http://www.eclipse.org/legal/epl-v10.html".
sl@0: *
sl@0: * Initial Contributors:
sl@0: * Nokia Corporation - initial contribution.
sl@0: *
sl@0: * Contributors:
sl@0: *
sl@0: * Description: 
sl@0: *
sl@0: */
sl@0: 
sl@0: 
sl@0: #include <e32std.h>
sl@0: #include <convdata.h>
sl@0: 
sl@0: #define ARRAY_LENGTH(aArray) (sizeof(aArray)/sizeof((aArray)[0]))
sl@0: 
sl@0: LOCAL_D const SCnvConversionData::SVariableByteData::SRange asciiVariableByteDataRanges[]=
sl@0: 	{
sl@0: 		{
sl@0: 		0x00,
sl@0: 		0xff,
sl@0: 		0,
sl@0: 		0
sl@0: 		}
sl@0: 	};
sl@0: 
sl@0: LOCAL_D const SCnvConversionData::SOneDirectionData::SRange asciiToUnicodeDataRanges[]=
sl@0: 	{
sl@0: 		{
sl@0: 		0x00,
sl@0: 		0x7f,
sl@0: 		SCnvConversionData::SOneDirectionData::SRange::EDirect,
sl@0: 		0,
sl@0: 		0,
sl@0: 			{
sl@0: 			0,
sl@0: 			0
sl@0: 			}
sl@0: 		}
sl@0: 	};
sl@0: 
sl@0: LOCAL_D const SCnvConversionData::SOneDirectionData::SRange unicodeToAsciiDataRanges[]=
sl@0: 	{
sl@0: 		{
sl@0: 		0x0000,
sl@0: 		0x007f,
sl@0: 		SCnvConversionData::SOneDirectionData::SRange::EDirect,
sl@0: 		1,
sl@0: 		0,
sl@0: 			{
sl@0: 			0,
sl@0: 			0
sl@0: 			}
sl@0: 		}
sl@0: 	};
sl@0: 
sl@0: GLREF_D const SCnvConversionData asciiConversionData=
sl@0: 	{
sl@0: 	SCnvConversionData::EUnspecified,
sl@0: 		{
sl@0: 		ARRAY_LENGTH(asciiVariableByteDataRanges),
sl@0: 		asciiVariableByteDataRanges
sl@0: 		},
sl@0: 		{
sl@0: 		ARRAY_LENGTH(asciiToUnicodeDataRanges),
sl@0: 		asciiToUnicodeDataRanges
sl@0: 		},
sl@0: 		{
sl@0: 		ARRAY_LENGTH(unicodeToAsciiDataRanges),
sl@0: 		unicodeToAsciiDataRanges
sl@0: 		},
sl@0: 	NULL,
sl@0: 	NULL
sl@0: 	};
sl@0: 
sl@0: GLREF_C void IsCharacterSetAscii(TInt& aConfidenceLevel, const TDesC8& aSample)
sl@0: 	{
sl@0: 	// loop through the aSample text checking the range of the character
sl@0: 	// If greater than 127 then it's not ASCII (gotta be harsh!)  ... 
sl@0: 	TInt sampleLength = aSample.Length();
sl@0: 	if (sampleLength == 0)
sl@0: 		{
sl@0: 		aConfidenceLevel = 91;
sl@0: 		return;
sl@0: 		}
sl@0: 	aConfidenceLevel = 100;
sl@0: 	
sl@0: 	
sl@0: 	_LIT8(KAsciiEsc,"\x28\x42");
sl@0: 	_LIT8(KJisRomanEsc,"\x28\x4a");
sl@0: 	_LIT8(KJisCEsc,"\x24\x40");
sl@0: 	_LIT8(KJisX0208Esc,"\x24\x42");
sl@0: 	_LIT8(KJisX0212Esc,"\x24\x28\x44");
sl@0: 	_LIT8(KHz1Esc,"\x7e\x7e");
sl@0: 	_LIT8(KHz2Esc,"\x7e\x7b");
sl@0: 	_LIT8(KHz3Esc,"\x7e\x7b");
sl@0: 	
sl@0: 	TInt asciiResult = 0;
sl@0: 	TInt jisRomanResult = 0; 
sl@0: 	TInt jisCResult = 0;
sl@0: 	TInt jisX0208Result =0;
sl@0: 	TInt jisX0212Result =0;
sl@0: 	TInt hz1Result=0;
sl@0: 	TInt hz2Result=0;
sl@0: 	TInt hz3Result=0;
sl@0: 	
sl@0: 	TInt escSequences = 0; 
sl@0: 	TInt controls = 0;
sl@0: 
sl@0: 
sl@0: 	for (TInt i = 0; i < sampleLength; ++i)
sl@0: 		{
sl@0: 		if ((aSample[i]&0x80)!=0x00)
sl@0: 			{
sl@0: 			aConfidenceLevel = 0;
sl@0: 			break;
sl@0: 			}
sl@0: 
sl@0: 		if (i > asciiResult)
sl@0: 			{
sl@0: 			asciiResult=(aSample.Right(sampleLength-i)).Find(KAsciiEsc);
sl@0: 			if (asciiResult!=KErrNotFound) //aConfidenceLevel-=2;
sl@0: 				escSequences += 2;
sl@0: 			}
sl@0: 
sl@0: 		if (i > jisRomanResult)
sl@0: 			{
sl@0: 			jisRomanResult=(aSample.Right(sampleLength-i)).Find(KJisRomanEsc);
sl@0: 			if (jisRomanResult!=KErrNotFound) //aConfidenceLevel-=2;
sl@0: 				escSequences += 2;
sl@0: 			}
sl@0: 
sl@0: 		if (i > jisCResult)
sl@0: 			{
sl@0: 			jisCResult=(aSample.Right(sampleLength-i)).Find(KJisCEsc);
sl@0: 			if (jisCResult!=KErrNotFound) //aConfidenceLevel-=2;
sl@0: 				escSequences += 2;
sl@0: 			}
sl@0: 
sl@0: 		if (i > jisX0208Result)
sl@0: 			{
sl@0: 			jisX0208Result=(aSample.Right(sampleLength-i)).Find(KJisX0208Esc);
sl@0: 			if (jisX0208Result!=KErrNotFound) //aConfidenceLevel-=2;
sl@0: 				escSequences += 2;
sl@0: 			}
sl@0: 
sl@0: 		if (i > jisX0212Result)
sl@0: 			{
sl@0: 			jisX0212Result=(aSample.Right(sampleLength-i)).Find(KJisX0212Esc);
sl@0: 			if (jisX0212Result!=KErrNotFound) //aConfidenceLevel-=2;
sl@0: 				escSequences += 2;
sl@0: 			}
sl@0: 
sl@0: 		if (i > hz1Result)
sl@0: 			{
sl@0: 			hz1Result=(aSample.Right(sampleLength-i)).Find(KHz1Esc);
sl@0: 			if (hz1Result!=KErrNotFound) //aConfidenceLevel-=2;
sl@0: 				escSequences += 2;
sl@0: 			}
sl@0: 
sl@0: 		if (i > hz2Result)
sl@0: 			{
sl@0: 			hz2Result=(aSample.Right(sampleLength-i)).Find(KHz2Esc);
sl@0: 			if (hz2Result!=KErrNotFound) //aConfidenceLevel-=2;
sl@0: 				escSequences += 2;
sl@0: 			}
sl@0: 
sl@0: 		if (i > hz3Result)
sl@0: 			{
sl@0: 			hz3Result=(aSample.Right(sampleLength-i)).Find(KHz3Esc);
sl@0: 			if (hz3Result!=KErrNotFound) //aConfidenceLevel-=2;
sl@0: 				escSequences += 2;
sl@0: 			}
sl@0: 
sl@0: 		if (aSample[i]==0x7f)
sl@0: 			// 0x7f is the control code for delete ... 
sl@0: 			{
sl@0: 			aConfidenceLevel = 0;
sl@0: 			break;
sl@0: 			}
sl@0: 
sl@0: 		 if (aSample[i]==0x1b)
sl@0: 			{
sl@0: 			static const TInt smsExtensionTable[12] = 
sl@0: 				{0x0a, 0x14, 0x1b, 0x24, 0x28, 0x29, 0x2f, 0x3c, 0x3d, 0x3e, 0x40, 0x65};
sl@0: 			for (TInt j=0; j < 12; ++j) // change the hard coded number to the Array length 
sl@0: 				{
sl@0: 				TInt increment1 = i+1;
sl@0: 				if (increment1 >= sampleLength)
sl@0: 					break;
sl@0: 				if (aSample[increment1] == smsExtensionTable[j])
sl@0: 					{
sl@0: 					aConfidenceLevel-=5;
sl@0: 					// /x1b/x24 & /x1b/x28 are the first two characters of a few
sl@0: 					// of  JIS & ISO2022JP escape sequence (That's why 0x24 was added in smsExtensionTable)
sl@0: 					// So if what's up next matches any JIS & IS02022JP escape sequence..... more deduction 
sl@0: 					// of the confidence Level 
sl@0: 					TInt increment2 = i+2;
sl@0: 					TInt increment3 = i+3;
sl@0: 					if((increment2 >= sampleLength)||((increment3) >= sampleLength))
sl@0: 						break;
sl@0: 					if (smsExtensionTable[j]==0x24)
sl@0: 						{
sl@0: 						// 24 -> 40,42 (28,44)
sl@0: 						if ((aSample[increment2]==0x40) || (aSample[increment2]==0x42) ||
sl@0: 							((aSample[increment2]==0x28)&&(aSample[increment3]==0x44)))
sl@0: 							{
sl@0: 							aConfidenceLevel=0;
sl@0: 							break;
sl@0: 							}
sl@0: 						}
sl@0: 					else if (smsExtensionTable[j]==0x28)
sl@0: 						{
sl@0: 						// 28 -> 42, 49, 4a
sl@0: 						if ((aSample[increment2]==0x42) || (aSample[increment2]==0x49) || (aSample[increment2]==0x4a))
sl@0: 							{
sl@0: 							aConfidenceLevel=0;
sl@0: 							break;
sl@0: 							}
sl@0: 						}
sl@0: 					}
sl@0: 				}
sl@0: 			if(aConfidenceLevel==0)
sl@0: 				break;
sl@0: 			}
sl@0: 			if (controls < 100 && aSample[i] < 0x20 && 	aSample[i] != '\r' && aSample[i] != '\n' && aSample[i] != '\t')
sl@0: 			// a few more control codes besides LF, CR, TAB 
sl@0: 			{
sl@0: 			controls ? controls *= 3 : controls = 3; 
sl@0: 			}
sl@0: 		}
sl@0: 		
sl@0: 	aConfidenceLevel -= controls;
sl@0: 	aConfidenceLevel = aConfidenceLevel - ((escSequences*100)/sampleLength);
sl@0: 	aConfidenceLevel =(aConfidenceLevel >0)? aConfidenceLevel: 0;
sl@0: 
sl@0: 
sl@0: 	}
sl@0: 
sl@0: